Peter Henderson

Holistic Agent Leaderboard: The Missing Infrastructure for AI Agent Evaluation

AutoCode: LLMs as Problem Setters for Competitive Programming

Safety Alignment Should be Made More Than Just a Few Tokens Deep

SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

On Evaluating the Durability of Safeguards for Open-Weight LLMs

Fantastic Copyrighted Beasts and How (Not) to Generate Them